Image model
MiniMax H3 Image
MiniMax H3 Image is MiniMax’s dedicated image model, post-trained from H3 for text-to-image and editing from up to 16 references, with native output up to 4K.
minimax/h3-imageAPI
Call MiniMax H3 Image
Every model takes the same request, so switching to MiniMax H3 Image is a change to the model field. These samples are written for its own contract and send as they are.
Specifications
What MiniMax H3 Image accepts
Read from the same registry the API validates against. A request outside it is refused when the task is created, before anything is charged.
Modes and inputs
- Text → Image
- Prompt only
- Image → Image
- 1–16 images · required
- The model picks its own output size
Output
- Aspect ratios
- 1:1
- 4:3
- 3:4
- 3:2
- 2:3
- 5:4
- 4:5
- 16:9
- 9:16
- 2:1
- 1:2
- 21:9
- 9:21
- 3:1
- 1:3
Leave out
size, or sendauto, and Mynth picks one for the prompt. Any other ratio snaps to the closest of these. Sizes- 4K
- Yes · any ratio with
_4k, such as16:9_4k
Prompt
- Negative prompt
- Not supported. Dropped before the provider call, no error
The contract as GET /models returns it
{
"modes": {
"txt->img": {},
"img->img": {
"inputs": {
"rules": [
{
"type": "image",
"min": 1,
"max": 16
}
]
}
}
}
}Pricing
What it costs
Pay per result, in USD, with no subscription. A failed image or video costs nothing. How pricing works
Rates
- Image
- $0.03 / image
- Image at 4K
- $0.09 / image
- Input image
- $0.01 / input
An input is charged once for every image it goes into: two inputs on four images are eight input charges.
Estimate a request
1 × $0.03
Held when the task is created. Only images that succeed are charged.